Predicting Ten-Year Clinical Outcomes in Multiple Sclerosis with Radiomics-Based Machine Learning Models

Background and purpose: Identifying patients with MS at higher risk of clinical progression is essential to inform clinical management. We aimed to build prognostic models by using machine learning (ML) algorithms predicting long-term clinical outcomes based on a systematic mapping of volumetric, radiomic, and macrostructural disconnection features from routine brain MRI scans of patients with MS. Materials and methods: In this longitudinal monocentric study, 3T structural MRI scans of patients with MS were retrospectively analyzed. Based on a 10-year clinical follow-up (average duration = 9.4 +/- 1.1 years), patients were classified according to confirmed disability progression (CDP) and cognitive impairment (CI) as assessed through the Expanded Disability Status Scale and the Brief International Cognitive Assessment of Multiple Sclerosis battery, respectively. Three-dimensional T1-weighted and FLAIR images were automatically segmented to obtain volumes, disconnection scores (estimated based on lesion masks and normative tractography data), and radiomic features from 116 GM regions defined according to the automated anatomic labeling atlas. Three ML algorithms (Extra Trees, Logistic Regression, and Support Vector Machine) were used to build models predicting long-term CDP and CI based on MRI-derived features. Feature selection was performed on the training set with a multistep process, and models were validated with a holdout approach, randomly splitting the patients into training (75%) and test (25%) sets. Results: We studied 177 patients with MS (men/women = 51/126; mean +/- standard deviation age: 35.2 +/- 8.7 years). Long-term CDP and CI were observed in 71 and 55 patients, respectively. Regarding the CDP class prediction analysis, the feature selection identified 13-, 12-, and 10-feature subsets obtaining an accuracy on the test set of 0.71, 0.69, and 0.67 for the Extra Trees, Logistic Regression, and Support Vector Machine classifiers, respectively. Similarly, for the CI prediction, subsets of 16, 17, and 19 features were selected, with 0.69, 0.64, and 0.62 accuracy values on the test set, respectively. There were no significant differences in accuracy between ML models for CDP (P = .65) or CI (P = .31). Conclusions: Building on quantitative features derived from conventional MRI scans, we obtained long-term prognostic models, potentially informing patients' stratification and clinical decision-making.